Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1438
    Prev
    Next
    INDEX
    Explanations

    scientific publication identifiers or citation formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers within the "Phys. Rev." journal references

    np_acts-logits-general · gemini-2.0-flash

    Physical Review B / D volumes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.82
     raiſ
    -0.75
     disambiguazione
    -0.72
     Thebes
    -0.70
     houſe
    -0.69
     للمعارف
    -0.69
     bezeichneter
    -0.67
     myſelf
    -0.67
     AssemblyCulture
    -0.67
    脚注の使い方
    -0.65
    POSITIVE LOGITS
     Lu
    0.51
     lu
    0.45
    settled
    0.45
     settle
    0.45
     art
    0.44
     a
    0.44
     filtering
    0.43
    wert
    0.42
     Ordnung
    0.42
     bộ
    0.41
    Activations Density 0.134%

    No Known Activations